<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ingestion on Jamal Yusuf</title><link>https://jamal.dev/tags/ingestion/</link><description>Recent content in Ingestion on Jamal Yusuf</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 17 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jamal.dev/tags/ingestion/index.xml" rel="self" type="application/rss+xml"/><item><title>The Boring Go Layer Between Your RAG Demo and Production</title><link>https://jamal.dev/writing/go-rag-ingestion-pipelines/</link><pubDate>Wed, 17 Jun 2026 00:00:00 +0000</pubDate><guid>https://jamal.dev/writing/go-rag-ingestion-pipelines/</guid><description>&lt;p&gt;RAG demos are seductive. Chunk a PDF. Embed. Retrieve. Watch the answer sparkle. Applause. Next slide.&lt;/p&gt;
&lt;p&gt;Production RAG is a &lt;strong&gt;pipeline problem&lt;/strong&gt; — documents that change, access policies that differ by team, embeddings that stale, audits that ask where a paragraph came from three quarters ago. The demo never shows that part. The on-call engineer lives there.&lt;/p&gt;
&lt;p&gt;I keep choosing Go for the unglamorous middle between source systems and vector indexes. Not because Python cannot embed. Because &lt;strong&gt;operations is a language choice too&lt;/strong&gt;.&lt;/p&gt;</description></item></channel></rss>